seedinteger
Random seed (0-2147483647) for reproducible results. Omit for a random seed; the same seed may still produce slightly different results.
Minimum: 0
Maximum: 2147483647
Wan 3.0 Pro Prime Video Edit
alibaba/wan/3.0/pro/prime/video-editWan 3.0 Pro Prime Video Edit by Alibaba restyles or modifies an input video from a text instruction, optionally guided by reference images and audio, keeping the original length, upscaled to 1080p, 2K, or 4K.
Try the model
Playground
Input
Text instruction describing the editing. Refer to the input video as Video 1 and to reference images or audio as Image 1, Audio 1, and so on.
URL of the input video (MP4 or MOV; 1-15 seconds, at least 16 fps, 240-4096px per side, under 100MB).
Output resolution tier after FlashVSR super-resolution.
Advanced settings
PNG, JPEG, WebP, or GIF · 20 MiB maximum each · up to 10
Up to 10 optional reference image URLs (JPEG, PNG, BMP, or WebP; up to 20MB each). Refer to them in the prompt as Image 1, Image 2, and so on.
Up to 5 optional reference audio URLs (WAV or MP3; 1-15s each, 15s total, under 15MB each).
Generate a synchronized audio track. Pricing is the same either way.
Random seed (0-2147483647) for reproducible results. Omit for a random seed; the same seed may still produce slightly different results. Range: 0 to 2147483647.
ResultIdle
Your output will appear here
Complete the inputs, then click Run.
Wan 3.0 Pro Prime Video Edit
Change an existing clip with a sentence: restyle it, swap a subject or prop, or rework the setting. Optional reference images and audio guide the change. The result keeps the length and framing of the source. Pro runs the same Wan 3.0 Prime model, then upscales the result with FlashVSR, so output comes back at 1080p, 2K, or 4K. For 480p or 720p use the non-Pro endpoints.
Pro Prime is the faster Wan 3.0 Pro tier: the same inputs and output quality as Wan 3.0 Pro, with significantly shorter end-to-end generation time and a higher per-second rate. Use Wan 3.0 Pro for batch or background jobs where turnaround does not matter.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 5,000 characters. |
video | video URL, required | — | Source clip, Video 1 in the prompt. MP4/MOV, 1–15s, ≥16fps, 240–4096px per side, ≤100MB. |
images | image URL[] (≤10) | — | Referenced as Image 1, Image 2, … |
audios | audio URL[] (≤5) | — | WAV/MP3, 1–15s each, 15s total, ≤15MB. Referenced as Audio 1, … |
resolution | 1080p / 2k / 4k | 1080p | Output tier after FlashVSR super-resolution; sets the per-second rate. |
generate_audio | boolean | true | Native dialogue, music, and effects. Same price on or off. |
seed | integer 0–2147483647 | random | Fix it to compare prompt changes. |
There is no duration field; the output is as long as the source.
Billing
Like the Wan 3.0 Pro rate, billing counts the source clip and the edited output, which are the same length, so each source second bills twice: $0.52 at 1080p, $0.56 at 2K, $0.62 at 4K. References are not metered.
| Source clip | Billed | 1080p | 2K | 4K |
|---|---|---|---|---|
| 2s | 4s | $1.04 | $1.12 | $1.24 |
| 5s | 10s | $2.60 | $2.80 | $3.10 |
| 10s | 20s | $5.20 | $5.60 | $6.20 |
| 15s | 30s | $7.80 | $8.40 | $9.30 |
The quote shown before submission assumes a 5-second source ($2.60 at 1080p); the final charge uses the measured length. Failed runs are not charged. Output files are copied to SandBase storage and the returned URL stays valid for 7 days; download anything you need to keep.
Prompting
- Lead with the change and state what must stay: “turn the scene into clay animation; keep her face and the camera motion”.
- Refer to the source as Video 1 and to references as Image 1 or Audio 1.
- Draft on the non-Pro video-edit endpoint at 480p, then rerun here for the final tier; edits cost twice the source length.
Limits
- The output aspect ratio follows the source video.
- To add new footage after the clip, use video-extend.
Also on SandBase
Other Wan 3.0 Pro Prime endpoints: alibaba/wan/3.0/pro/prime/video (all modes in one schema), alibaba/wan/3.0/pro/prime/text-to-video, alibaba/wan/3.0/pro/prime/image-to-video, alibaba/wan/3.0/pro/prime/reference-to-video, alibaba/wan/3.0/pro/prime/video-extend. Standard tier: alibaba/wan/3.0/pro/video-edit.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/wan/3.0/pro/prime/video-edit",
"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260402/ldnfdf/wan2.7-videoedit-style-change.mp4",
"resolution": "1080p",
"generate_audio": true
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
videostringrequired
URL of the input video (MP4 or MOV; 1-15 seconds, at least 16 fps, 240-4096px per side, under 100MB).
audiosarray
Up to 5 optional reference audio URLs (WAV or MP3; 1-15s each, 15s total, under 15MB each).
imagesarray
Up to 10 optional reference image URLs (JPEG, PNG, BMP, or WebP; up to 20MB each). Refer to them in the prompt as Image 1, Image 2, and so on.
promptstringrequired
Text instruction describing the editing. Refer to the input video as Video 1 and to reference images or audio as Image 1, Audio 1, and so on.
resolutionstring
Output resolution tier after FlashVSR super-resolution.
Default: "1080p"
Possible values: "1080p", "2k", "4k"
generate_audioboolean
Generate a synchronized audio track. Pricing is the same either way.
Default: true
{
"model": "alibaba/wan/3.0/pro/prime/video-edit",
"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260402/ldnfdf/wan2.7-videoedit-style-change.mp4",
"resolution": "1080p",
"generate_audio": true
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
No example output has been published yet. Use Playground → Result → JSON after a completed run to inspect your response.